1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
;
; Copyright (c) 2014 The WebM project authors. All Rights Reserved.
;
; Use of this source code is governed by a BSD-style license
; that can be found in the LICENSE file in the root of the source
; tree. An additional intellectual property rights grant can be found
; in the file PATENTS. All contributing project authors may
; be found in the AUTHORS file in the root of the source tree.
;
%define private_prefix vp10
%include "third_party/x86inc/x86inc.asm"
; This file provides SSSE3 version of the forward transformation. Part
; of the macro definitions are originally derived from the ffmpeg project.
; The current version applies to x86 64-bit only.
SECTION .text
%if ARCH_X86_64
; matrix transpose
%macro INTERLEAVE_2X 4
punpckh%1 m%4, m%2, m%3
punpckl%1 m%2, m%3
SWAP %3, %4
%endmacro
%macro TRANSPOSE8X8 9
INTERLEAVE_2X wd, %1, %2, %9
INTERLEAVE_2X wd, %3, %4, %9
INTERLEAVE_2X wd, %5, %6, %9
INTERLEAVE_2X wd, %7, %8, %9
INTERLEAVE_2X dq, %1, %3, %9
INTERLEAVE_2X dq, %2, %4, %9
INTERLEAVE_2X dq, %5, %7, %9
INTERLEAVE_2X dq, %6, %8, %9
INTERLEAVE_2X qdq, %1, %5, %9
INTERLEAVE_2X qdq, %3, %7, %9
INTERLEAVE_2X qdq, %2, %6, %9
INTERLEAVE_2X qdq, %4, %8, %9
SWAP %2, %5
SWAP %4, %7
%endmacro
%macro HMD8_1D 0
psubw m8, m0, m1
psubw m9, m2, m3
paddw m0, m1
paddw m2, m3
SWAP 1, 8
SWAP 3, 9
psubw m8, m4, m5
psubw m9, m6, m7
paddw m4, m5
paddw m6, m7
SWAP 5, 8
SWAP 7, 9
psubw m8, m0, m2
psubw m9, m1, m3
paddw m0, m2
paddw m1, m3
SWAP 2, 8
SWAP 3, 9
psubw m8, m4, m6
psubw m9, m5, m7
paddw m4, m6
paddw m5, m7
SWAP 6, 8
SWAP 7, 9
psubw m8, m0, m4
psubw m9, m1, m5
paddw m0, m4
paddw m1, m5
SWAP 4, 8
SWAP 5, 9
psubw m8, m2, m6
psubw m9, m3, m7
paddw m2, m6
paddw m3, m7
SWAP 6, 8
SWAP 7, 9
%endmacro
INIT_XMM ssse3
cglobal hadamard_8x8, 3, 5, 10, input, stride, output
lea r3, [2 * strideq]
lea r4, [4 * strideq]
mova m0, [inputq]
mova m1, [inputq + r3]
lea inputq, [inputq + r4]
mova m2, [inputq]
mova m3, [inputq + r3]
lea inputq, [inputq + r4]
mova m4, [inputq]
mova m5, [inputq + r3]
lea inputq, [inputq + r4]
mova m6, [inputq]
mova m7, [inputq + r3]
HMD8_1D
TRANSPOSE8X8 0, 1, 2, 3, 4, 5, 6, 7, 9
HMD8_1D
mova [outputq + 0], m0
mova [outputq + 16], m1
mova [outputq + 32], m2
mova [outputq + 48], m3
mova [outputq + 64], m4
mova [outputq + 80], m5
mova [outputq + 96], m6
mova [outputq + 112], m7
RET
%endif
|
